• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

News

UX and Data hackaton

Seminar of the Research Group "Machine learning and social computing" on 10th of November was held in an unusual format for its participants UX and data hackathon associated with educational design.

Online communities of practice

In the meantime, we continue to work with student groups on the topics related to the Research Group. A week ago, a second group seminar was held, devoted to the study of virtual communities of practice on the GitHub and StackOverflow platforms. 

Visualization in scientific research

This year, we have decided to expand the format of work with students through the organization of student projects on the topics of our Research Group. The first one was devoted tothe analysis of the role of data visualization in social sciences.

Participants of our Research Group at SocInfo'18

Members of our Research Group presented their poster “Network structure of e-shops profile as factor of its success: case of VK.com” at the 10th International Conference on Social Informatics, which was held in Saint Petersburg 25-28th of September (by the way, the 9th was held in Oxford, and the 11th will be held in Qatar).

Data scraping with web services and R

On Saturday the seminar of the Research Group "Machine Learning and Social Computing" was held. It included a workshop on data scraping and further discussion of its research application.

Our Research Group at "The International Conference on the Foundations of Digital Games"

On 8-10 of August, an international conference on game research and development called The International Conference on the Foundations of Digital Games (FDG) was held in Malmo, Sweden. A student of the Higher School of Economics, Roman Poyane, and a participant of the RG “Machine Learning and Social Computing” Denis Bulygin presented their works about chat communication on game-streaming websites at the workshop “All the World (Wide Web)'s A Stage: A Twitch Workshop”, organized as part of the conference.

Networks travelling. Machine Learning and Social Computing at NetGloW conference

NetGloW conference was held from 4th till 6th of July at the St. Petersburg State University and was devoted to networks analysis. It is organized every two years by the Center for German and European Studies. Participants of our Research Group not only presented their research but also were organizers of the session “Social Networks as Valuation Devices: Reputation, Ranking, Recommendations”.

Participants of our Research Group at Sunbelt'18

Members of our Research Group presented their projects at Sunbelt 2018 conference which was held in Utrecht, the Netherlands from June 26 to July 1. It is a leading conference devoted to Social Network Analysis which started its history in 1981. This year, it was attended by more than 600 people who are interested in the implementation of SNA in the diverse scientific fields such as sociology, mathematics, anthropology, epidemiology, etc.

Cybersport research

Cybersport is a vital and debatable topic for the scientific society. For example, it is still unclear whether eSports can be called as a type of traditional sports or not. Even though such questions are still unanswerable, on the 28th of April Ksenia Konstantinova, Vsevolod Suschevskiy, and Ekaterina Marchenko told the audience about several important for the eSports themes during the regular research group seminar: broadcasts of the major tournaments and transfers between cybersport teams.

TrueSkills: rating systems

When evaluating the success of a team is not sophisticated processes, according to an out-of-date Elo rating model is often used, which evaluates only victory or defeat, improperly works with a draw, and ignores individual players in a team with different experience. At the first in 2018 seminar Research Group "Machine Learning and Social Computing" Alexander Sirotkin on the example of the game "What? Where? When?" told about the TrueSkill rating system, and how to improve it, by giving the greater contribution of the leader and estimation of cases where the team played in the incomplete composition.